Prompt Injection Scanner MCP Server: Install & Setup

Install Prompt Injection Scanner in Claude Code

Claude Code

claude mcp add --transport http prompt-injection-scanner https://injectionscan.openkrill.app/mcp

mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)

{
  "mcpServers": {
    "prompt-injection-scanner": {
      "url": "https://injectionscan.openkrill.app/mcp"
    }
  }
}

Check text before your agent reads it: hidden instructions, invisible characters and links that leak data.

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Remote. Hosted by the provider. You connect with a URL, nothing to install.

Run: claude mcp add --transport http prompt-injection-scanner https://injectionscan.openkrill.app/mcp

Layered prompt-injection checks for LLM hosts; 100 welcome credits on signup.

pollinations/model-context-protocol

Multimodal MCP server for generating images, audio, and text with no authentication required

Agent identity, scoped access, and proof across tools. Check authority before an agent acts.

Public phishing-domain feed: check a domain, search detections by brand, and pivot on campaigns and certs.

Notarize AI outputs, audits and agreements on the TON blockchain, with nothing stored server-side.

Agent threat intel: wallet sanctions screening, wallet and domain age, hostname reputation; paid STIX 2.1 feed via x402.